Backtesting Trading Strategies with GAN To Avoid Overfitting
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 106 === Many works have shown the overfitting hazard of selecting a trading strategy based only on good IS (in sample) performance. But most of them have merely shown such phenomena exist without offering ways to avoid them. We propose an approach to avoid overfitting:...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/232z9x |
id |
ndltd-TW-106NTU05392114 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-106NTU053921142019-07-25T04:46:48Z http://ndltd.ncl.edu.tw/handle/232z9x Backtesting Trading Strategies with GAN To Avoid Overfitting 應用GAN於回測交易策略以避免過擬合 Ao Sun 孫奧 碩士 國立臺灣大學 資訊工程學研究所 106 Many works have shown the overfitting hazard of selecting a trading strategy based only on good IS (in sample) performance. But most of them have merely shown such phenomena exist without offering ways to avoid them. We propose an approach to avoid overfitting: A good (meaning non-overfitting) trading strategy should still work well on paths generated in accordance with the distribution of the historical data. We use GAN with LSTM to learn or fit the distribution of the historical time series . Then trading strategies are backtested by the paths generated by GAN to avoid overfitting 呂育道 2018 學位論文 ; thesis 44 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 106 === Many works have shown the overfitting hazard of selecting a trading strategy based only on good IS (in sample) performance. But most of them have merely shown such phenomena exist without offering ways to avoid them. We propose an approach to avoid overfitting: A good (meaning non-overfitting) trading strategy should still work well on paths generated in accordance with the distribution of the historical data. We use GAN with LSTM to learn or fit the distribution of the historical time series . Then trading strategies are backtested by the paths generated by GAN to avoid overfitting
|
author2 |
呂育道 |
author_facet |
呂育道 Ao Sun 孫奧 |
author |
Ao Sun 孫奧 |
spellingShingle |
Ao Sun 孫奧 Backtesting Trading Strategies with GAN To Avoid Overfitting |
author_sort |
Ao Sun |
title |
Backtesting Trading Strategies with GAN To Avoid Overfitting |
title_short |
Backtesting Trading Strategies with GAN To Avoid Overfitting |
title_full |
Backtesting Trading Strategies with GAN To Avoid Overfitting |
title_fullStr |
Backtesting Trading Strategies with GAN To Avoid Overfitting |
title_full_unstemmed |
Backtesting Trading Strategies with GAN To Avoid Overfitting |
title_sort |
backtesting trading strategies with gan to avoid overfitting |
publishDate |
2018 |
url |
http://ndltd.ncl.edu.tw/handle/232z9x |
work_keys_str_mv |
AT aosun backtestingtradingstrategieswithgantoavoidoverfitting AT sūnào backtestingtradingstrategieswithgantoavoidoverfitting AT aosun yīngyòngganyúhuícèjiāoyìcèlüèyǐbìmiǎnguònǐhé AT sūnào yīngyòngganyúhuícèjiāoyìcèlüèyǐbìmiǎnguònǐhé |
_version_ |
1719230000247341056 |